Abnormal battery cell identification method, computer equipment and computer readable storage medium

Abstract

The invention discloses an abnormal battery cell identification method, computer equipment and a computer readable storage medium, and belongs to the technical field of power batteries, the identification method comprises the following steps: obtaining voltage data of a plurality of battery cells, and calculating a voltage drop of each battery cell under a standing condition based on the voltage data; for each battery cell, polymerizing the voltage drops under the plurality of standing working conditions in a first preset time period to obtain a polymerization result; and identifying an abnormal battery cell from the plurality of battery cells based on the aggregation result of each battery cell. The abnormal battery cell data is identified by using the outlier degree of the voltage drop of the battery cells in the battery pack under the standing working condition, the data validity is good, the identification result accuracy is high, and the use safety of the battery pack is ensured.

Description

Technical Field

[0001] The present application belongs to the field of power battery technology, and in particular relates to a method for identifying abnormal battery cells, a computer device, and a computer-readable storage medium. Background Art

[0002] A battery pack is a device composed of a specific number of battery cells used to store and release electrical energy. Currently, it is primarily used in new energy vehicles to provide kinetic energy. During vehicle-side use, the cells within a battery pack degrade at varying rates due to factors such as poor internal cell consistency, long-term rapid charging cycles, and prolonged high-temperature storage. Some cells degrade and degrade faster than others. These cells with rapidly degrading electrical performance are referred to as abnormal cells or outliers within the pack. The presence of abnormal cells can lead to reduced usable capacity of the entire pack, reduced battery life, and inaccurate remaining charge (SOC) calculations. If the abnormal cells continue to degrade rapidly, they can cause serious consequences such as thermal runaway, compromising the safety of the battery pack. Due to the complexity and enclosed nature of battery packs, accurate electrochemical performance of all cells within the pack cannot be accurately determined during market operation, making identification of abnormal cells difficult.

[0003] To this end, this application aims to propose a solution that can identify abnormal cells in a battery pack that is put into operation on the market without disassembling the battery pack. Summary of the Invention

[0004] In order to overcome the above-mentioned defects, the abnormal battery cell identification method, computer device and computer-readable storage medium proposed in this application can be used to solve or at least partially solve the technical problem of difficulty in identifying abnormal battery cells in the prior art.

[0005] In a first aspect, the present application provides a method for identifying abnormal battery cells, comprising: acquiring voltage data of a plurality of battery cells, and calculating a voltage drop of each of the battery cells under a static working condition based on the voltage data;

[0006] For each of the battery cells, aggregating voltage drops under multiple static working conditions within a first preset time period to obtain an aggregated result;

[0007] Based on the aggregation result of each of the battery cells, an abnormal battery cell is identified from the plurality of battery cells.

[0008] In some embodiments, the step of identifying an abnormal battery cell from the plurality of battery cells based on the aggregated result of each battery cell comprises:

[0009] When the absolute value of the aggregation result of the battery cell is greater than a threshold, determining that the battery cell is an outlier;

[0010] identifying abnormal cells from the plurality of cells based on a determination result of whether each cell is outlier;

[0011] The threshold is obtained according to the following formula:

[0012] 3σ=cv_drop_mean+3×cv_drop_std;

[0013] Wherein, 3σ is the threshold, cv_drop_mean is the mean value of the aggregation result, and cv_drop_std is the standard deviation of the aggregation result.

[0014] The step of identifying an abnormal battery cell from the plurality of battery cells based on a result of determining whether each battery cell is out of the group comprises:

[0015] Counting the number of outliers of each of the battery cells within a second preset time period;

[0016] Based on the outlier count of each of the battery cells, abnormal battery cells are identified from the plurality of battery cells.

[0017] In some embodiments, the identifying abnormal battery cells from the plurality of battery cells based on the aggregation result of each battery cell further includes:

[0018] Obtaining multiple aggregation results for each of the battery cells;

[0019] For each of the battery cells, plotting a life cycle curve according to multiple aggregation results of the battery cell;

[0020] According to the characteristics of the life cycle curve, it is determined whether the battery cell is abnormal.

[0021] In some implementation schemes, the stationary operating condition includes at least one of the following: an operating condition corresponding to when the vehicle relay is disconnected and the vehicle is parked and the engine is turned off; and an operating condition corresponding to when the vehicle relay is closed and the vehicle is not turned off and the vehicle is stationary.

[0022] The voltage data includes at least a first voltage value at the beginning of the static operating condition and a second voltage value at the end of the static operating condition;

[0023] Calculating the voltage drop of each of the battery cells under static conditions based on the voltage data includes: calculating the difference between the first voltage value and the second voltage value to obtain the voltage drop.

[0024] In some embodiments, calculating the voltage drop of each of the battery cells under static conditions based on the voltage data includes:

[0025] A relaxation voltage curve is determined according to the voltage data, and a voltage difference of each battery cell within a preset relaxation time interval is calculated based on the relaxation voltage curve and determined as the voltage drop under the static working condition.

[0026] In some implementation schemes, after obtaining the voltage data of the plurality of battery cells, the method further includes: deleting battery balancing data from the voltage data.

[0027] In a second aspect, the present application provides a computer device comprising a processor and a storage device, wherein the storage device is suitable for storing multiple program codes, and the program codes are suitable for being loaded and run by the processor to execute the abnormal battery cell identification method described in any one of the technical solutions of the above-mentioned abnormal battery cell identification method.

[0028] In a third aspect, the present application provides a computer-readable storage medium storing a plurality of program codes, wherein the program codes are suitable for being loaded and run by a processor to execute the abnormal battery cell identification method described in any one of the technical solutions of the above-mentioned abnormal battery cell identification method.

[0029] The above one or more technical solutions of this application have at least one or more of the following beneficial effects:

[0030] In implementing the technical solution of the present application, the voltage data of multiple battery cells are first obtained, and the voltage drop of each battery cell under static conditions is calculated based on the voltage data; then, for each battery cell, the voltage drops under multiple static conditions within a first preset time period are aggregated to obtain an aggregated result; based on the aggregated result of each battery cell, without disassembling the battery pack, abnormal batteries can be identified from the multiple battery cells using only the acquired battery cell data. The present application solution uses the degree of outlier of the voltage drop of the battery cells in the battery pack under static conditions to identify abnormal batteries, which can avoid the differences in attenuation mechanisms between battery packs of the same model and effectively identify abnormal batteries in the pack. At the same time, the identification method of the present invention is calculated based on the voltage data of the battery cells in the battery pack under static conditions. Static conditions occur frequently during use in the market, and the data is easily computable. In addition, the present invention avoids the influence of different SOCs, different temperatures, different driving habits, etc. in the battery pack on the identification results through data aggregation processing, improves the recognition accuracy and feasibility, and can effectively identify abnormal batteries in the battery pack to ensure the safety of the battery pack. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The disclosure of this application will be more easily understood with reference to the accompanying drawings. Those skilled in the art will readily appreciate that these drawings are for illustrative purposes only and are not intended to limit the scope of protection of this application. Furthermore, similar numbers in the figures represent similar components, where:

[0032] Figure 1 This is a flow chart of the main steps of a method for identifying abnormal cells according to an embodiment of the present application;

[0033] Figure 2This is a schematic diagram of a no-load relaxation voltage curve of all cells in a battery pack under a stationary condition obtained based on cell data uploaded by a battery swap station in an embodiment of the present application;

[0034] Figure 3 is based on Figure 2 The diagram shows the slope distribution of the no-load relaxation voltage curve;

[0035] Figure 4 and Figure 5 Schematic diagrams of voltage drop change effects of an embodiment of the present application where data aggregation processing is not adopted and where data aggregation processing is adopted;

[0036] Figure 6 A schematic diagram of statistical analysis results of the number of outliers of all cells in a battery pack according to an embodiment of the present application;

[0037] Figure 7 This is a schematic block diagram of a device for identifying abnormal battery cells according to an embodiment of the present application. DETAILED DESCRIPTION

[0038] Some embodiments of the present application are described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present application and are not intended to limit the scope of protection of the present application.

[0039] In the description of this application, "module" and "processor" may include hardware, software, or a combination of both. A module may include hardware circuitry, various suitable sensors, communication ports, and memory. It may also include software components, such as program code, or a combination of software and hardware. A processor may be a central processing unit, a microprocessor, an image processor, a digital signal processor, or any other suitable processor. A processor has data and / or signal processing capabilities. A processor may be implemented in software, hardware, or a combination of both. Non-transitory computer-readable storage media include any suitable medium capable of storing program code, such as magnetic disks, hard disks, optical disks, flash memory, read-only memory, random access memory, etc. The term "A and / or B" refers to all possible combinations of A and B, such as only A, only B, or both A and B. The terms "at least one of A or B" or "at least one of A and B" have similar meanings to "A and / or B" and may include only A, only B, or both A and B. The singular forms "a" and "the" may also include the plural forms.

[0040] The preferred embodiments of the present application are described below in conjunction with the drawings in the specification. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application and are not used to limit the present application. In addition, the embodiments and features in the embodiments of the present application can be combined with each other if there is no conflict.

[0041] With the widespread development and adoption of new energy vehicles, the cycle life and safety of battery packs, which serve as power sources, have attracted increasing attention. Typically, a battery pack system consists of hundreds of cells, interconnected in series and parallel, with complex internal structures. However, cell production carries certain process risks, and abnormalities in cells during market operation can affect the safety of the battery pack. Therefore, the market urgently needs to develop a method to monitor and identify abnormal cells within the pack.

[0042] The abnormal cell identification method provided by the present application is a solution for monitoring and identifying abnormal cells in power battery packs of new energy vehicles based on cloud data, which is realized by developing an algorithm in the cloud to identify outlier cells in the pack by utilizing the degree of outlier of the static voltage drop between the cells in the battery pack. At present, a battery management system (BMS) is usually installed in the battery pack of a vehicle, which can facilitate the battery pack to record and upload the current, voltage, temperature and other information of the whole pack of cells to the cloud in real time during the operation of the market end. In addition, during the period when the vehicle is connected to the battery swap station for charging and the period when it is stationary after charging, the battery swap station can also collect and upload the battery pack data in the vehicle to the cloud. Therefore, the abnormal cell identification method of the present invention can be calculated based on the voltage data of the full-cell static working condition in the battery pack collected and uploaded to the cloud by the BMS or the battery swap station. The static working condition occurs frequently during the use of the market end, and the data is well computable. In addition, the present invention avoids the influence of the differences in the attenuation mechanisms between battery packs on the recognition results by means of data aggregation, which helps to improve the recognition accuracy and feasibility.

[0043] See attached Figure 1 , Figure 1 This is the main step flow of an abnormal battery cell identification method in an embodiment of the present application.

[0044] Step S101: obtaining voltage data of a plurality of battery cells, and calculating a voltage drop of each battery cell under a static working condition based on the voltage data.

[0045] In one embodiment, this step may be to obtain voltage data of all battery cells in the battery pack under static conditions, and calculate the voltage drop of each battery cell under static conditions based on the voltage data.

[0046] One implementation of this step may specifically include step a1 and step a2:

[0047] Step a1: Based on the cell data uploaded to the cloud by the BMS inside the battery pack, filter and obtain the voltage data of the cell corresponding to the static working condition.

[0048] Wherein, the static operating condition includes at least one of the following: the operating condition corresponding to when the vehicle relay is disconnected, the vehicle is parked and the ignition is turned off and the vehicle is stationary; the operating condition corresponding to when the vehicle relay is closed and the vehicle is not turned off and the vehicle is stationary. In combination with actual application scenarios, when the voltage data of the battery cells corresponding to the static operating condition are obtained by screening and obtaining only the voltage data of the battery cells under the operating condition of the vehicle relay being disconnected, the vehicle is parked and the ignition is turned off and the vehicle is stationary, since battery balancing may exist under this operating condition, the voltage static drop calculated based on the voltage data under this operating condition may cause the voltage drop values ​​of some battery cells to be significantly abnormal. In order to improve the validity of the data and reduce the impact of balancing on the data, preferably, when filtering and obtaining the voltage data, the voltage data of the battery cells under the operating conditions corresponding to when the vehicle relay is disconnected, the vehicle is parked and the ignition is turned off and the vehicle is stationary, i.e., the voltage data of the battery cells under the two operating conditions corresponding to when the vehicle relay is disconnected, the vehicle is parked and the ignition is turned off and the vehicle relay is closed and the vehicle is not turned off and the vehicle is stationary, can be obtained at the same time to calculate the voltage drop, so as to enhance the data, improve the validity of the data, and reduce the impact of battery balancing on the abnormal battery cell identification results.

[0049] It will be appreciated that an EIT (Electrical Impedance Tomography) dataset collected during a cycle of current application and voltage measurement is typically referred to as a frame. In this embodiment, the cell data uploaded to the cloud by the vehicle includes the last frame of voltage data obtained through voltage measurement before the vehicle enters a static state, as well as voltage data during the static state, where the voltage data during the static state includes the frame of voltage data before the static state ends. In this embodiment, the voltage data corresponding to the cell in the static state obtained by screening and acquiring includes at least a first voltage value of the cell measured before the start of the static state, denoted as cv_start_vol, and a second voltage value of the cell measured before the end of the static state, denoted as cv_end_vol.

[0050] Step a2: Calculate the difference between the first voltage value and the second voltage value to obtain the voltage drop.

[0051] It should be understood that the voltage drop is also called potential difference or voltage difference. The voltage drop in the embodiment of the present application can be understood as the difference between voltages measured at two time points. For example, the voltage drop is recorded as cv_drop, then cv_drop=cv_start_vol-cv_end_vol.

[0052] Another implementation of this step may specifically include step b1 and step b2:

[0053] Step b1: Based on the battery cell data uploaded to the cloud by the battery swap station, filter and obtain the voltage data of the battery cells corresponding to the static working conditions.

[0054] Among them, the static operating condition refers to the operating condition corresponding to when the vehicle is stationary after being fully charged at the battery swap station.

[0055] Step b2: determining a relaxation voltage curve according to the voltage data, calculating the voltage difference of each battery cell within a preset relaxation time interval based on the relaxation voltage curve, and determining it as the voltage drop under the static working condition.

[0056] In this embodiment, because the battery swap station can continuously power the data transmission process of uploading the battery cell data in the battery pack to the cloud, without the need for power supply from the battery pack on the vehicle side, the battery cell data uploaded by the battery swap station can be used to obtain the continuous no-load relaxation voltage curve corresponding to the static working condition. The voltage data under the complete static working condition is analyzed by the relaxation voltage curve, and more detailed data feature values ​​can be extracted within a specific static time such as the preset relaxation time interval. Specifically in this embodiment, it is assumed that the preset relaxation time interval is (t1, t2), for example, t1 = 8000s, t2 = 15000s; the voltage values ​​corresponding to t1 and t2 on the relaxation voltage curve are v1 and v2 respectively, and the pressure difference is recorded as △V, then △V = v1-v2, that is, the voltage drop cv_drop determined based on the pressure difference within the preset relaxation time interval is equal to △V.

[0057] Optionally, the embodiment of the present application can also determine the relaxation voltage curve in the following manner: for the vehicle-end battery under static conditions, wake-up detection is performed at preset time intervals, a segment of the relaxation voltage curve is obtained based on the voltage data of the battery cell obtained from each wake-up detection, and the complete relaxation voltage curve is obtained based on multiple segments obtained from multiple wake-up detections.

[0058] Furthermore, based on the relaxation voltage curve, on the one hand, the voltage drop can be obtained, and abnormal cells can be identified based on the degree of outliers in the voltage drop; on the other hand, the slope value k of the relaxation voltage curve can also reflect the voltage drop rate in the depolarization section of the cell, so abnormal cells can also be identified based on the degree of outliers in the k value. For example, Figure 2 The figure shows the no-load relaxation voltage curve of all cells in the battery pack under a static condition, which is obtained based on the cell data uploaded by the battery swap station. Figure 2 The slope value k corresponding to each curve in the time interval t ime is calculated for the curve shown in , and the distribution of k values ​​of all cells in the battery pack is plotted based on the calculation results. Figure 3 As shown, from Figure 3 It can be seen that there is an obvious outlier k value, and the battery cell corresponding to the k value in the battery pack can be identified as an abnormal battery cell.

[0059] Optionally, after obtaining the voltage data of the plurality of battery cells, the method further includes: deleting cell balancing data from the voltage data. The cell balancing data refers to voltage data measured when cell balancing is enabled.

[0060] During the use of battery packs in the market, in order to compensate for the inconsistency of SOC differences between cells, a balancing method is used. Regardless of active balancing or passive balancing, the existence of balancing will affect the calculation of the static voltage drop, resulting in obvious abnormal voltage drop values ​​of some cells, which are identified as abnormal self-discharge cells during statistics. Therefore, by deleting the voltage data measured when cell balancing is turned on in the data, the impact of the differences in attenuation mechanisms between battery packs on the recognition results can be avoided, which helps to improve the accuracy and feasibility of recognition. For battery packs with active balancing, when uploading data to the cloud, the voltage data measured when cell balancing is turned on will be marked with a balancing mark. Therefore, the deletion of the voltage data corresponding to the voltage data measured when cell balancing is turned on can be specifically: deleting the voltage data with the balancing mark in the voltage data.

[0061] For earlier-produced battery packs, since only passive balancing exists, it is impossible to identify which voltage data corresponds to the voltage data measured with battery balancing enabled based on the data uploaded to the cloud. As a result, there may be errors in the calculated voltage drop. To avoid this error, in the embodiments of the present application, the impact of balancing can be reduced to a certain extent through data aggregation processing.

[0062] Step S102: for each of the battery cells, aggregating voltage drops under multiple static working conditions within a first preset time period to obtain an aggregation result.

[0063] Specifically in this embodiment, the first preset time period is preferably one day. This step can be specifically to aggregate the voltage drops of each battery cell under all static working conditions every day to obtain the aggregation result.

[0064] It should be understood that the first preset time period in this embodiment may also be one month or other custom time period, and the aggregation method may be data summation or other data aggregation methods.

[0065] For example, taking the voltage data obtained by filtering in step S101 as including voltage data measured with cell balancing enabled, for example, a certain battery cell is in a static operating condition four times in one day, and cell balancing is enabled in the first two static operating conditions and the last static operating condition, but not in the third static operating condition. Figure 4 The figure shows the voltage drop change diagram of a certain battery cell under four static conditions in one day without polymerization treatment of the battery cell's voltage drop. It can be seen from the figure that under the last static condition, due to the activation of the equalization, the voltage drop calculation result of the battery cell is obviously abnormal, that is, the value of cv_drop is significantly increased, about 3.15. The vertical axis in the figure represents cv_drop and the horizontal axis represents the operating condition. Figure 5This is a schematic diagram of the change in the voltage drop aggregation results of the battery cells after the voltage drop data is aggregated by day. It can be seen from the figure that after the voltage drop data of the battery cells is aggregated by day, the voltage drop value is significantly reduced to about 2.387. Figure 4 and Figure 5 It can be seen from the comparison that the influence of battery balancing data can be significantly eliminated through data aggregation processing. If data aggregation processing is not performed on a daily basis, the battery cell will be mistakenly reported as an abnormal battery cell. Therefore, the data processing method of step S102 in this embodiment helps to improve the accuracy of the abnormal battery cell identification result.

[0066] Step S103: Based on the aggregation result of each battery cell, identify abnormal battery cells from the plurality of battery cells.

[0067] This step S103 specifically includes: when the absolute value of the aggregation result of the battery cell is greater than a threshold, determining that the battery cell is outliers; and identifying abnormal batteries from the plurality of battery cells based on the determination result of whether each battery cell is outliers.

[0068] The threshold is obtained according to the following formula:

[0069] 3σ=cv_drop_mean+3×cv_drop_std;

[0070] Wherein, 3σ is the threshold, cv_drop_mean is the mean value of the aggregation result, and cv_drop_std is the standard deviation of the aggregation result.

[0071] For example, if the number of cells in a battery pack is n, then Wherein ∑cv_drop is the aggregation result.

[0072] The method of identifying abnormal cells from the plurality of cells based on the determination result of whether each cell is outlier comprises: counting the number of outliers of each cell within a second preset time period; and identifying abnormal cells from the plurality of cells based on the number of outliers of each cell.

[0073] The statistical method of the number of outliers in this embodiment is as follows: the aggregation result of each battery cell is compared with the threshold value to determine the number of outliers of the battery cell; specifically, in this embodiment, the initial value of the number of outliers of each battery cell in the battery pack is 0, and for each battery cell, it is determined whether the aggregation result of its voltage drop exceeds the threshold value. If so, the number of outliers of the battery cell is increased by one, otherwise the number of outliers remains unchanged.

[0074] In this embodiment, the method for identifying abnormal cells in a battery pack based on the number of outliers is as follows: the number of outliers of each cell obtained by counting within the second preset time period is compared with the preset alarm number, and when the number of outliers of a cell exceeds the preset alarm number, the cell is identified as an abnormal cell. It should be understood that the second preset time period is greater than the first preset time period, and the second preset time period can be a custom duration, or a duration determined based on the entire pack throughput of the battery pack. For example, the second preset time period can be a custom 3 months, or 24 hours determined based on the entire pack throughput of the battery pack (such as the time taken when the battery pack charge and discharge capacity reaches 300kwh).

[0075] In addition, the preset alarm times in this embodiment can be a custom set value. Further, the preset alarm times can be set to multiple values ​​in combination with actual applications to achieve the effect of multiple alarm prompts. For example, when the number of outliers is greater than the preset alarm times of 0, it indicates that there is a safety risk in the battery cell. When the number of outliers is greater than the preset alarm times of 5, it indicates that there is a more serious safety risk in the battery cell.

[0076] For example, take a new energy vehicle battery pack as an example. The battery pack capacity is 100kwh, and there are 96 cells in the battery pack, all connected in series. In this example, with a statistical period of three months, the statistical analysis results of the number of outliers of all cells in the battery pack are as follows: Figure 6 As shown in the figure, the number of times the 55# cell is out of the group reaches 18 times. Assuming that the preset alarm number is 5, based on Figure 6 The analysis results shown can identify cell 55# as the abnormal cell in the battery pack.

[0077] The above step S103 may further include: obtaining multiple aggregation results of each of the battery cells; drawing a life cycle curve for each of the battery cells according to the multiple aggregation results of the battery cells; and determining whether the battery cell is abnormal according to the characteristics of the life cycle curve.

[0078] See attached Figure 7 , Figure 7 This is a main structural block diagram of an abnormal cell identification device according to an embodiment of the present application. In practical applications, the device can be configured in the cloud to monitor and identify abnormal cells. Figure 7 As shown, the abnormal battery cell identification device provided in this embodiment mainly includes a data acquisition module 201, a data aggregation module 202 and a result identification module 203, wherein:

[0079] A data acquisition module 201 is configured to acquire voltage data of a plurality of battery cells and calculate a voltage drop of each battery cell under static working conditions based on the voltage data;

[0080] In this embodiment, the static operating condition includes at least one of the following: a condition corresponding to a vehicle relay being disconnected and the vehicle being parked and ignited; and a condition corresponding to a vehicle relay being closed and the vehicle being ignited. The voltage data includes at least a first voltage value at the beginning of the static operating condition and a second voltage value at the end of the static operating condition.

[0081] The data acquisition module 201 may include a first calculation unit and / or a second calculation unit;

[0082] The first calculation unit is configured to calculate a difference between the first voltage value and the second voltage value to obtain the voltage drop.

[0083] The second calculation unit is used to determine a relaxation voltage curve according to the voltage data, calculate the voltage difference of each battery cell within a preset relaxation time interval based on the relaxation voltage curve, and determine it as the voltage drop under the static working condition.

[0084] The data acquisition module 201 may further include a data deletion unit;

[0085] The data deleting unit is configured to delete the cell balancing data from the voltage data.

[0086] a data aggregation module 202 for aggregating voltage drops of each battery cell under multiple static working conditions within a first preset time period to obtain an aggregation result;

[0087] The result identification module 203 is configured to identify abnormal cells from the plurality of cells based on the aggregation result of each cell.

[0088] The above-mentioned result identification module 203 may include a comparison unit and an identification unit;

[0089] The comparing unit is configured to determine that the battery cell is an outlier when the absolute value of the aggregation result of the battery cell is greater than a threshold;

[0090] The threshold is obtained according to the following formula:

[0091] 3σ=cv_drop_mean+3×cv_drop_std;

[0092] Wherein, 3σ is the threshold, cv_drop_mean is the mean value of the aggregation result, and cv_drop_std is the standard deviation of the aggregation result.

[0093] The identification unit is used to identify abnormal battery cells from multiple battery cells based on the determination result of whether each battery cell is outliers; for example, within a second preset time period, the number of outliers of each battery cell is counted; and based on the number of outliers of each battery cell, the abnormal battery cell is identified from multiple battery cells.

[0094] The result recognition module 203 may also include an acquisition unit and a judgment unit;

[0095] The acquiring unit is configured to acquire multiple aggregation results of each of the battery cells;

[0096] The judgment unit is configured to draw a life cycle curve for each battery cell according to multiple aggregation results of the battery cell; and judge whether the battery cell is abnormal according to characteristics of the life cycle curve.

[0097] For ease of explanation, the introduction to the above-mentioned abnormal battery cell identification device only shows the part related to the embodiment of the present application. For specific technical details not disclosed, please refer to the method part of the embodiment of the present application.

[0098] It should be understood that since the configuration of each module or unit is merely for the purpose of illustrating the functional units of the present application, the physical device corresponding to these modules or units may be the processor itself, or a portion of the software in the processor, a portion of the hardware, or a combination of software and hardware. Therefore, the number of modules in the figure is merely illustrative.

[0099] Those skilled in the art will appreciate that the various modules or units in the device can be adaptively split or merged. Such splitting or merging of specific modules or units will not cause the technical solution to deviate from the principles of this application. Therefore, the technical solutions after splitting or merging will fall within the scope of protection of this application.

[0100] Those skilled in the art will appreciate that all or part of the process of implementing the method of the above embodiment of the present application can also be completed by instructing related hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of each of the above method embodiments can be implemented. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form.

[0101] Furthermore, the present application also provides a computer device.

[0102] In an embodiment of a computer device according to the present application, the computer device primarily includes a processor and a storage device. The storage device may be configured to store a program for executing the abnormal cell identification method of the above-described method embodiment, and the processor may be configured to execute the program in the storage device, including but not limited to a program for executing the abnormal cell identification method of the above-described method embodiment. For ease of illustration, only the portion relevant to the embodiment of the present application is shown. For specific technical details not disclosed, please refer to the method portion of the embodiment of the present application.

[0103] In the embodiment of the present application, the computer device may be a control device device formed by various electronic devices. In some possible implementations, the computer device may include multiple storage devices and multiple processors. The program for executing the abnormal cell identification method of the above method embodiment can be divided into multiple subroutines, and each subroutine can be loaded and run by the processor to execute different steps of the abnormal cell identification method of the above method embodiment. Specifically, each subroutine can be stored in different storage devices respectively, and each processor can be configured to execute the program in one or more storage devices to jointly implement the abnormal cell identification method of the above method embodiment, that is, each processor executes different steps of the abnormal cell identification method of the above method embodiment respectively to jointly implement the abnormal cell identification method of the above method embodiment.

[0104] The aforementioned multiple processors may be processors deployed on the same device. For example, the aforementioned computer device may be a high-performance device composed of multiple processors, and the aforementioned multiple processors may be processors configured on the high-performance device. Furthermore, the aforementioned multiple processors may also be processors deployed on different devices. For example, the aforementioned computer device may be a server cluster, and the aforementioned multiple processors may be processors on different servers in the server cluster.

[0105] Furthermore, the present application also provides a computer-readable storage medium.

[0106] In a computer-readable storage medium embodiment according to the present application, the computer-readable storage medium can be configured to store a program for executing the abnormal cell identification method of the above-mentioned method embodiment, and the program can be loaded and run by the processor to implement the above-mentioned abnormal cell identification method. For ease of explanation, only the parts related to the embodiment of the present application are shown. For specific technical details not disclosed, please refer to the method part of the embodiment of the present application. The computer-readable storage medium can be a storage device formed by various electronic devices. Optionally, the computer-readable storage medium in the embodiment of the present application is a non-transitory computer-readable storage medium.

[0107] Thus far, the technical solutions of the present application have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is readily understood by those skilled in the art that the scope of protection of the present application is obviously not limited to these specific embodiments. Without departing from the principles of the present application, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present application.

Claims

1. A method for identifying abnormal battery cells, characterized in that: The method comprises: Acquire voltage data of a plurality of battery cells, and calculate a voltage drop of each of the battery cells under a static working condition based on the voltage data; For each of the battery cells, aggregating voltage drops under multiple static working conditions within a first preset time period to obtain an aggregated result; Based on the aggregation result of each of the battery cells, an abnormal battery cell is identified from the plurality of battery cells.

2. The abnormal cell identification method according to claim 1, characterized in that: The step of identifying abnormal cells from the plurality of cells based on the aggregation result of each cell comprises: When the absolute value of the aggregation result of the battery cell is greater than a threshold, determining that the battery cell is outlier; Based on the determination result of whether each battery cell is outlier, identifying an abnormal battery cell from the plurality of battery cells; The threshold is obtained according to the following formula: 3σ=cv_drop_mean+3×cv_drop_std; Among them, 3σ is the threshold, cv_drop_mean is the mean value of the aggregation result, and cv_drop_std is the standard deviation of the aggregation result.

3. The abnormal cell identification method according to claim 2, characterized in that: The step of identifying an abnormal cell from the plurality of cells based on a determination result of whether each cell is out of the group comprises: Within a second preset time period, counting the number of outliers of each of the battery cells; Based on the outlier count of each of the battery cells, an abnormal battery cell is identified from the plurality of battery cells.

4. The abnormal cell identification method according to any one of claims 1 to 3, characterized in that: The step of identifying abnormal cells from the plurality of cells based on the aggregation result of each cell further includes: Obtaining multiple aggregation results for each of the battery cells; For each of the battery cells, a life cycle curve is drawn according to a plurality of aggregation results of the battery cell; Whether the battery cell is abnormal is determined based on the characteristics of the life cycle curve.

5. The abnormal cell identification method according to any one of claims 1 to 3, characterized in that: The stationary operating condition includes at least one of the following: an operating condition corresponding to when the vehicle relay is disconnected and the vehicle is parked and the engine is turned off; and an operating condition corresponding to when the vehicle relay is closed and the vehicle is not turned off and the engine is turned off.

6. The abnormal cell identification method according to any one of claims 1 to 3, characterized in that: The voltage data at least includes a first voltage value at the beginning of the static working condition and a second voltage value at the end of the static working condition; Calculating the voltage drop of each of the battery cells under static conditions based on the voltage data includes: calculating the difference between the first voltage value and the second voltage value to obtain the voltage drop.

7. The abnormal battery cell identification method according to any one of claims 1 to 3, characterized in that: The calculating the voltage drop of each of the battery cells under the static working condition based on the voltage data comprises: A relaxation voltage curve is determined according to the voltage data, and a voltage difference of each of the battery cells within a preset relaxation time interval is calculated based on the relaxation voltage curve and determined as the voltage drop under the static working condition.

8. The abnormal cell identification method according to any one of claims 1 to 3, characterized in that: After the voltage data of the plurality of battery cells are obtained, the method further includes: The cell balancing data is deleted from the voltage data.

9. A computer device comprising a processor and a storage device, wherein the storage device is suitable for storing a plurality of program codes, characterized in that: The program code is suitable for being loaded and run by the processor to execute the abnormal battery cell identification method according to any one of claims 1 to 8.

10. A computer-readable storage medium storing a plurality of program codes, characterized in that: The program code is suitable for being loaded and run by a processor to execute the abnormal battery cell identification method according to any one of claims 1 to 8.

Images